Palinode — the complete, unedited output of the deterministic mcptrustchecker engine v1.9.0, scanned . Every finding, capability tag and score component below is exactly what the engine produced — no AI, no post-processing.
{
"tool": {
"name": "mcptrustchecker",
"version": "1.9.0",
"methodologyVersion": "mcptrustchecker-1.9"
},
"target": {
"id": "palinode",
"source": {
"kind": "package",
"origin": "palinode"
},
"server": {
"name": "palinode"
}
},
"grade": "A",
"score": {
"score": 93,
"threatScore": 100,
"grade": "A",
"band": "A",
"categorySubtotals": {
"injection": 0,
"exfiltration": 0,
"permissions": 0,
"supply-chain": 0,
"network": 0,
"hygiene": 0
},
"vector": [
{
"kind": "client",
"term": "capability-exposure",
"level": "high",
"label": "capability blast radius (high) — client exposure if the model is manipulated",
"appliedPenalty": 6
},
{
"kind": "client",
"term": "verification-discount",
"level": "repo",
"label": "publisher verification (public source) — no provenance, but the source is public and inspectable",
"appliedPenalty": 1
},
{
"kind": "client",
"term": "coverage-honesty",
"level": "source",
"label": "inspection depth (source) — how much of the target the scan could see",
"appliedPenalty": 0
}
],
"gatesFired": [],
"methodologyVersion": "mcptrustchecker-1.9"
},
"capability": {
"level": "high",
"reasons": [
"ingests untrusted external content (a prompt-injection entry point)",
"can execute shell commands or code"
],
"tags": [
"untrusted-input",
"code-exec"
]
},
"coverage": {
"level": "source",
"inputs": {
"toolSurface": true,
"implementationSource": true,
"packageMetadata": true,
"liveTransport": false
},
"caveats": [
"Tools were statically extracted from the published source (30 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command \"npx -y <package>\"."
]
},
"findings": [
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (palinode/api/routers/health.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`palinode/api/routers/health.py:72`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "palinode/api/routers/health.py"
},
"evidence": "try: unpushed = subprocess.run( [\"git\", \"rev-list\", \"--count\", \"origin/main..HEAD\"], cwd",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "palinode/api/routers/health.py",
"line": 72,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (palinode/api/routers/memory.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`palinode/api/routers/memory.py:781`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "palinode/api/routers/memory.py"
},
"evidence": "push = subprocess.run( [\"git\", \"push\"], cwd=config.palinode_dir, check=False,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "palinode/api/routers/memory.py",
"line": 781,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (palinode/cli/__init__.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`palinode/cli/__init__.py:211`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "palinode/cli/__init__.py"
},
"evidence": "try: subprocess.run([\"sudo\", \"systemctl\", \"stop\", svc], check=True) console.print(f\"[gree",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "palinode/cli/__init__.py",
"line": 211,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (palinode/cli/mcp_smoke.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`palinode/cli/mcp_smoke.py:114`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "palinode/cli/mcp_smoke.py"
},
"evidence": "top\" proc = subprocess.run( # nosec B603,B607 - argv form, no shell [\"pgrep\", \"-f\", pattern",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "palinode/cli/mcp_smoke.py",
"line": 114,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (palinode/cli/worktree.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`palinode/cli/worktree.py:36`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "palinode/cli/worktree.py"
},
"evidence": "etedProcess: return subprocess.run( # nosec B603,B607 - argv form, no shell [\"git\", *args], cwd=cwd, captur",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "palinode/cli/worktree.py",
"line": 36,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (palinode/consolidation/write_time.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`palinode/consolidation/write_time.py:462`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "palinode/consolidation/write_time.py"
},
"evidence": "g.palinode_dir) subprocess.run( [\"git\", \"add\", rel], cwd=config.palinode_dir,",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "palinode/consolidation/write_time.py",
"line": 462,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (palinode/core/git_tools.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`palinode/core/git_tools.py:49`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "palinode/core/git_tools.py"
},
"evidence": "deliberately — never ``shell=True``, never string-interpolated commands — so user-supplied inputs (file paths, comm",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "palinode/core/git_tools.py",
"line": 49,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (palinode/diagnostics/checks/git_remote.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`palinode/diagnostics/checks/git_remote.py:29`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "palinode/diagnostics/checks/git_remote.py"
},
"evidence": "etedProcess: return subprocess.run( [\"git\", \"-C\", cwd, *args], capture_output=True, text=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "palinode/diagnostics/checks/git_remote.py",
"line": 29,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (palinode/diagnostics/checks/watcher.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`palinode/diagnostics/checks/watcher.py:53`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "palinode/diagnostics/checks/watcher.py"
},
"evidence": "try: result = subprocess.run( [\"ps\", \"-ef\"], capture_output=True, text=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "palinode/diagnostics/checks/watcher.py",
"line": 53,
"nonRuntime": false
}
},
{
"ruleId": "MTC-SRC-002",
"title": "Shell/command execution in server code (palinode/ingest/pipeline.py)",
"category": "permissions",
"severity": "high",
"confidence": "strong",
"description": "In the server's implementation (`palinode/ingest/pipeline.py:129`): Spawning a shell/process is command-execution capability; with unsanitized tool input it is command injection / RCE. This is read from the code itself — not from the tool description — so a poisoned server cannot hide it behind honest-looking metadata.",
"remediation": "Review this call path: confirm it never receives unsanitized tool input, constrain it, or remove it. Treat a server whose code reaches these sinks as high-capability regardless of what its tools claim.",
"location": {
"kind": "server",
"name": "palinode/ingest/pipeline.py"
},
"evidence": "r: result = subprocess.run( [\"pdftotext\", filepath, \"-\"], capture_output=Tru",
"owasp": "LLM05:2025 Improper Output Handling",
"data": {
"rule": "MTC-SRC-002",
"file": "palinode/ingest/pipeline.py",
"line": 129,
"nonRuntime": false
}
},
{
"ruleId": "MTC-CAP-007",
"title": "Unconstrained URL/host parameter \"url\" on \"palinode_ingest\"",
"category": "network",
"severity": "medium",
"confidence": "heuristic",
"description": "Tool \"palinode_ingest\" takes a URL/host parameter \"url\" with no allowlist/pattern. An outbound-request tool with an unbounded destination enables SSRF and cloud-metadata access (e.g. 169.254.169.254).",
"remediation": "Allowlist destinations or constrain the parameter; block private/link-local addresses server-side.",
"location": {
"kind": "tool",
"name": "palinode_ingest",
"field": "inputSchema.properties.url"
},
"owasp": "LLM06:2025 Excessive Agency",
"data": {
"param": "url"
}
}
],
"toxicFlows": [],
"capabilities": [
{
"tool": "palinode_session_init",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_list",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_read",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_search",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_save",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_ingest",
"tags": [
"untrusted-input"
],
"reasons": {
"untrusted-input": [
"keyword \"fetch\""
]
}
},
{
"tool": "palinode_status",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_history",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_timeline",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_entities",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_consolidate",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_archive_expired",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_archive",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_diff",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_blame",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_trace",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_rollback",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_push",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_trigger",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_session_end",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_lint",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_review",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_dedup_suggest",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_orphan_repair",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_cluster_neighbors",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_topic_coverage",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_doctor",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_doctor_deep",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_prompt",
"tags": [],
"reasons": {}
},
{
"tool": "palinode_depends",
"tags": [],
"reasons": {}
}
],
"surfaceDigest": "8f62ac51631e56b713714ec229d1ed00acb009681889e99d5ae958ae451e7b1c",
"stats": {
"tools": 30,
"prompts": 0,
"resources": 0,
"findingsBySeverity": {
"critical": 0,
"high": 10,
"medium": 1,
"low": 0,
"info": 0
}
}
}